Models you can run yourself
A model, every quantisation somebody made of it, and what each one costs to run.
Only one source knows: GGUF quantisations 2229 · Hugging Face models 63
Behind: zetlyn/models-hf has not completed an update.
Covers. Every GGUF repository created since 2026-08-23, and the base model behind each one. 2,684 of those bases are named; without a Hugging Face token the run is throttled off after roughly 600 to 750 of them, so the model side of the join is partial and the scope says so on its front page. Excludes. Ollama, whose library names no Hugging Face repository to join on. Benchmarks, which have no machine-readable source.
Compared · what is held against what, and from which column of each source
| Property | Hugging Face models | GGUF quantisations |
|---|---|---|
| Licence | cardData.license | cardData.license |
Everything else the sources say is shown side by side, and not compared.
Found
1–25 of 69| Thing | Kind | Licence | Downloads | Date |
|---|---|---|---|---|
| 0xWhiteMage/Qwen3.8-27B-Kearuga 0xWhiteMage/Qwen3.8-27B-Kearuga · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 2 | apache-2.0 | 1320 / 2525 / 2667 / 2842 | 2026-09-04 |
| aldair166/qwen3.5-2.8b aldair166/qwen3.5-2.8b · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 3 | apache-2.0 | 112 / 1183 / 1274 / 29 / 376 | 2026-09-07 |
| ApolloRaines/Qwen2.5-14B-Noncompliant ApolloRaines/Qwen2.5-14B-Noncompliant · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 2 | apache-2.0 | 1651 / 309 / 334 / 431 | 2026-09-19 |
| chenhaodev/tcm-qwen3-8b-lora chenhaodev/tcm-qwen3-8b-lora · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 163 / 76 / 83 | 2026-09-11 |
| danghuyhoang/qwen3-30b-vietnamese-instruct danghuyhoang/qwen3-30b-vietnamese-instruct · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 0 / 115 | 2025-11-08 |
| darrellbest/Qwen3-0.6B-Heretic darrellbest/Qwen3-0.6B-Heretic · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 221 / 235 / 248 | 2026-09-25 |
| flashback2k/FlashModel-Qwen3.5-9B flashback2k/FlashModel-Qwen3.5-9B · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 3 | apache-2.0 | 1112 / 1202 / 2782 / 362 / 377 | 2026-09-17 |
| ForSureTesterSim/Qwen3-14B-NSFW-FDA ForSureTesterSim/Qwen3-14B-NSFW-FDA · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 2 | apache-2.0 | 248 / 2556 / 262 / 6110 | 2026-08-25 |
| arghya2030/commercecore-qwen3-1.7b arghya2030/commercecore-qwen3-1.7b · Hugging Face models, GGUF quantisations · matched qwen | model 1 quantisation 1 | apache-2.0 | 459 / 492 | 2026-09-27 |
| dolev31/ProactiveInquirer-Qwen3-8B-Merged dolev31/ProactiveInquirer-Qwen3-8B-Merged · Hugging Face models, GGUF quantisations · matched qwen | model 1 quantisation 1 | apache-2.0 | 337 / 354 | 2026-09-27 |
| 5ivatej/LessThink-Qwen3-4B-v1 5ivatej/LessThink-Qwen3-4B-v1 · Hugging Face models, GGUF quantisations · matched qwen | model 1 quantisation 1 | apache-2.0 | 209 / 364 | 2026-09-29 |
| bytkim/Qwen3.8-27B-pi bytkim/Qwen3.8-27B-pi · Hugging Face models, GGUF quantisations · matched qwen | model 1 quantisation 1 | apache-2.0 | 2632 / 528 | 2026-09-29 |
| Cecilis/cultist-simulator-qwen3-4b Cecilis/cultist-simulator-qwen3-4b · Hugging Face models, GGUF quantisations · matched qwen | model 1 quantisation 1 | apache-2.0 | 386 / 415 | 2026-09-28 |
| Davv4/phishing-qwen3.5-2b Davv4/phishing-qwen3.5-2b · Hugging Face models, GGUF quantisations · matched qwen | model 1 quantisation 1 | apache-2.0 | 154 / 17 | 2026-06-05 |
| 0xSojalSec/Qwen3.8-27B-full-Uncensored 0xSojalSec/Qwen3.8-27B-full-Uncensored · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 2 | apache-2.0 | 1055 / 1631 / 1754 / 5106 | 2026-08-31 |
| 3MPER0RR/Qwen3.8-27B-3MPER0RR-abliterated 3MPER0RR/Qwen3.8-27B-3MPER0RR-abliterated · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 4 | apache-2.0 | 1210 / 2028 / 4327 / 6372 / 742 / 872 | 2026-08-31 |
| 3tic/Orion-Qwen3-4B-CPT-v2605 3tic/Orion-Qwen3-4B-CPT-v2605 · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 120 / 39 | 2026-05-18 |
| ahmetggg/Luck-Qwen3-4b-Code-FineTune ahmetggg/Luck-Qwen3-4b-Code-FineTune · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 1133 / 147 / 359 | 2026-08-31 |
| birgermoell/Qwen3.5-4B-EU-Tool birgermoell/Qwen3.5-4B-EU-Tool · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 31 / 32 / 433 | 2026-07-04 |
| Davidmg0815/qwen2.5-7b-spreizzaehler-v3 Davidmg0815/qwen2.5-7b-spreizzaehler-v3 · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 477 / 517 / 66 | 2026-09-21 |
| Davidmg0815/qwen2.5-7b-spreizzaehler-v4 Davidmg0815/qwen2.5-7b-spreizzaehler-v4 · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 1 | apache-2.0 | 145 / 151 / 78 | 2026-09-21 |
| empero-ai/Qwen3.8-2B-Distill empero-ai/Qwen3.8-2B-Distill · Hugging Face models · matched qwen | model 2 | apache-2.0 | 8041 | 2026-08-15 |
| empero-ai/Qwen3.8-4B-Distill empero-ai/Qwen3.8-4B-Distill · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 6 | apache-2.0 | 0 / 110 / 11939 / 12162 / 1844 / 518 / 995 | 2026-08-15 |
| empero-ai/Qwen3.8-9B-Distill empero-ai/Qwen3.8-9B-Distill · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 4 | apache-2.0 | 0 / 110 / 1348 / 13482 / 14943 / 679 | 2026-08-15 |
| EschaLabs/Qwen3.8-27B-Escha-W2 EschaLabs/Qwen3.8-27B-Escha-W2 · Hugging Face models, GGUF quantisations · matched qwen | model 2 quantisation 2 | apache-2.0 | 1775 / 1833 / 5092 / 530 | 2026-08-20 |
Facets
Licence 8160 of 10579 claims
apache-2.04983
Task 1343 of 10579 claims
Sources
Hugging Face models primary
The model itself: its licence, its task and how many people fetch it.
model · partial1568
GGUF quantisations high
Which quantisations exist, which is what decides whether it runs on the machine somebody has.
quantisation · current9011